Campaign Analytics Agent
Reports ROAS and acquisition cost by campaign.
- Industry
- Procure AI
- Department
- Marketing
- Team
- Demand Generation
- Kind
- Investigator
- Approver
- Marketing Lead
- Code
- MKT-09
It reports cost per sales-accepted lead, pipeline and won contract value by campaign and channel for a period, reconciles platform-reported conversions against the CRM, and explains what drove the change from the comparison period. Because managed procurement deals take months, it reads pipeline and won value on the attribution window the playbook sets. **The problem it solves:** Why cost per sales-accepted lead or pipeline per campaign changed from the comparison period: which campaigns, which channels, and whether spend, targeting, conversion or tracking drove it.
How it works
6 steps, and a person signs off before step 6.
- 01Looks it up
Finds the record the request is about in the analytics warehouse: campaign spend and conversions, joined with leads, pipeline and won contracts from the CRM..
- 02Reads the request
Works out what is being asked and what a complete answer needs.
- 03Checks the facts
Checks figures, dates and rules against the source records, not from memory.
- 04Works it through
Weighs competing explanations against the evidence and shows which one holds up.
- 05Asks a person
Hands the work to Marketing Lead with its reasoning before anything goes out.
- 06Acts
Once approved, it acts in the BI dashboard: it publishes the campaign report. and records what was done.
What it works with
Your knowledge, your systems, your people.
Knows
The attribution model, conversion definitions, target cost per sales-accepted lead and pipeline ratios, the sales cycle lengths by service line and the report audiences.
Reads from
the analytics warehouse: campaign spend and conversions, joined with leads, pipeline and won contracts from the CRM.
Acts in
the BI dashboard: it publishes the campaign report.
Hands back
An object with period, by_campaign (a list with campaign, spend, sales_accepted_leads, cost_per_sal, pipeline, won_value and change_percent), drivers (a list with driver, evidence and confidence) and gaps (a list).
Asks a person when
The report recommends cutting spend, the platform and CRM disagree by more than 15 percent, or the report goes to leadership.
Settings
Your limits, set by your managers.
| Setting | Default | What it controls |
|---|---|---|
| Attribution model | position-based | How credit is shared. |
| Target cost per sales-accepted lead (USD) | 450 | The target reported against. |
| Target pipeline per dollar | 15 | The pipeline target reported against. |
| Variance that is explained (%) | 20 | Changes larger than this are explained. |
| Platform and CRM gap that is flagged (%) | 15 | A larger gap is flagged. |
Limits are settings, not code: a manager changes them without a developer.
Rules it always follows
- Use position-based attribution and say so.
- Report against 450 per sales-accepted lead and 15 pipeline per dollar.
- Explain every change above 20 percent with the driver the evidence supports.
- Flag platform and CRM gaps above 15 percent; the CRM is the record.
- Won value counts only signed service contracts, never verbal awards.
See the Campaign Analytics Agent agent on your own work.
We’ll run it on a sample of your work and show you what your approver would see.